Search

Various applications leverage location data to increase transparency, efficiency, and safety in intralogistics. There are several properties of location data, such as the data's degrees of freedom, system latency, update rate, or accuracy. To select a suitable indoor localization system, corresponding data requirements must be derived by analyzing the considered application. To date, the dependencies of the system performance and location data requirements have not been satisfactorily described in the literature. Thus, no method exists to adequately derive location data requirements. For intralogistics, such a method is of particular relevance due to the high-cost sensitivity and heterogeneity of partially safety-relevant indoor localization applications. To fill this gap, a method for selecting and quantifying location data requirements for the application in intralogistics is presented in this work, creating substantial added value for warehouse managers and system integrators. The method is based on a spatial model that is built on the premise that location data is used to determine the presence or absence of an entity in a multidimensional interest space. The usage of the method is demonstrated in an exemplary case study for the application of 'Automated Pallet Booking'., Comment: Conference on Production Systems and Logistics (CPSL 2023)

Estimating the pose of a pallet and other logistics objects is crucial for various use cases, such as automatized material handling or tracking. Innovations in computer vision, computing power, and machine learning open up new opportunities for device-free localization based on cameras and neural networks. Large image datasets with annotated poses are required for training the network. Manual annotation, especially of 6D poses, is an extremely labor-intensive process. Hence, newer approaches often leverage synthetic training data to automatize the process of generating annotated image datasets. In this work, the generation of synthetic training data for 6D pose estimation of pallets is presented. The data is then used to train the Deep Object Pose Estimation (DOPE) algorithm. The experimental validation of the algorithm proves that the 6D pose estimation of a standardized Euro pallet with a Red-Green-Blue (RGB) camera is feasible. The comparison of the results from three varying datasets under different lighting conditions shows the relevance of an appropriate dataset design to achieve an accurate and robust localization. The quantitative evaluation shows an average position error of less than 20 cm for the preferred dataset. The validated training dataset and a photorealistic model of a Euro pallet are publicly provided.

Absolute position accuracy is the key performance criterion of an Indoor Localization System (ILS). Since ILS are heterogeneous and complex cyber-physical systems, the localization accuracy depends on various influences from the environment, system configuration, and the application processes. To determine the position accuracy of a system in a reproducible, comparable, and realistic manner, these factors must be taken into account. We propose a strategy for analyzing the influences on the position accuracy of ILS using decision trees in combination with application-related or technology-related categorization. The proposed strategy is validated using empirical data from 120 experiments. The accuracy of an Ultra-Wideband and a LiDAR-based ILS was determined under different application-driven influencing factors, considering the application of autonomous mobile robots in warehouses. Finally, the opportunities and limitations of analyzing decision trees to compare system performance, find a suitable system, optimize the environment or system configuration, and understand the relevance of different influencing factors are presented., Comment: Accepted for 2022 International Conference on Indoor Positioning and Indoor Navigation (IPIN), 5 - 7 Sep. 2022, Beijing, China

Despite their potential of increasing operational efficiency, transparency, and safety, the use of Localization and Tracking Systems (LTSs) in warehouse environments remains seldom. One reason is the lack of market transparency and stakeholder's trust in the systems' performance as a consequence of poor use of Test and Evaluation (T&E) methods and transferability of the obtained T&E results. The T&E 4Log (Test and Evaluation for Logistics) Framework was developed to examine how the transferability of T&E results to practical scenarios in warehouse environments can be increased. Conventional T&E approaches are integrated and extended under consideration of the warehouse environment, logistics applications, and domain-specific requirements, into an application-driven T&E framework. The application of the proposed framework in standard and application-dependent test cases leads to a set of performance criteria and corresponding application-specific requirements. This enables a well-founded identification of suitable LTSs for given warehouse applications. The T&E 4Log Framework was implemented at the Institute for Technical Logistics (ITL) and validated by T&E of a reflector-based Light Detection and Ranging (LiDAR) LTS, a contour-based LiDAR LTS, and an Ultra-Wideband (UWB) LTS for the exemplary applications Automated Pallet Booking, Goods Tracking, and Autonomous Forklift Navigation., Comment: Work-in-Progress Paper for the Eleventh International Conference on Indoor Positioning and Indoor Navigation (IPIN) 2021